During my work at the Luleå University of Technology, my research turned towards the condition monitoring and condition based maintenance of the systems. I developed a computational intelligence framework for the context-aware decision making for condition based maintenance of wind turbines. In this research work, I created metadata generation, relating ontologies and create decision-based rules for decision support for maintenance strategies.
My other research areas I found interesting are Big Data and Maintenance 4.0 in Railways, safety analysis and predictive analytics of mining machines, and hybrid modeling for bearings. I also looked into the impacts of Solar storms in Railway infrastructure which are low frequency and high consequence events society.
My present work is looking into the prediction of remaining useful life and predictive maintenance of switches and crossings (SC) in Railways. This can be carried out by track geometry modeling, data driven approaches for failure prediction and probability of failure prediction using probabilities approaches. I developed an effective strategy for opportunistic maintenance with functional testing for SCs. This involves the development of prediction methodologies and algorithms to provide the status based on the nowcasting and forecasting defined by the Train Management Systems (TMS). I am also interested in assessing the condition by condition monitoring techniques to predict the behavior in future using hybrid methodologies. The reliability is assessed using the probability of failure for scheduling preventive maintenance activities of TMS.